Alibaba Cloud: Paraformer v2
paraformer-v2- Price
- From $0.000012
- Modalities
- Audio
About Paraformer v2
Paraformer v2 is Alibaba's file-based speech recognition model for offline transcripts of meetings and long conversations. It is called asynchronously. Alibaba's native file service documents recordings up to 2 GB and 12 hours, while the upload endpoint linked here has a separate 25 MB limit. Compared with the real-time models it trades immediacy for a complete transcript.
Where it works well
- Alibaba's native file service documents recordings up to 12 hours or 2 GB; the upload endpoint linked here accepts files up to 25 MB.
- Timestamps are always included, so no extra option is needed to get them.
- Alibaba documents speaker diarization as a native option for meetings; it is not in the model details linked here.
- Alibaba documents sensitive-word filtering as a native option; it is not in the model details linked here.
When to choose another model
- Results arrive after the job completes; live captions need Paraformer Realtime v2.
- For 8 kHz phone recordings the 8K variant matches the audio better.
Getting started
Create API key
Create a key in Console, then use it with every model on the platform.
Send your first request
Copy the example for your language and run it against the endpoint.
Speech to textTokenLab endpointPOST/v1/audio/transcriptionscurl -X POST "https://api.tokenlab.sh/v1/audio/transcriptions" \ -H "Authorization: Bearer sk-xxx" \ -F file="@audio.mp3" \ -F operation="stt" \ -F response_format="json" \ -F model="paraformer-v2" \ -F language="en"
Parameters
Speech to text
| Parameter | Values and limits | Default | Notes |
|---|---|---|---|
file | Inputs: ≥ 1, ≤ 1 | Not provided | Send one audio file in multipart/form-data. Maximum file size is 25 MiB. |
language | Not provided | Not provided | This field is accepted. The current public contract does not specify a complete value range or list. No additional values are promised. The omitted-field default is not verified. |
response_format | Not provided | json | Omit this field to use json. The current route creates an asynchronous transcription task and returns JSON task status and results. This field does not select an audio output encoding. Other response formats have not been qualified for this model. |
Pricing
The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.
Speech to text
per second- Official price
- $0.00001176
- Verified price
- —
- Discount
- —
| Official priceper second | Verified priceper second | Discount | |
|---|---|---|---|
| Speech to text | $0.00001176 | — | — |
Usage & activity
Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.
Usage & availability
Last 24 hours- Requests
- Success rate
- P95 latency
- Total tokens
Data is based on aggregate user requests, excluding status checks.
Open in Console
Open Paraformer v2 in Console with a prompt ready to edit or send.
Help me try paraformer-v2 with a short audio request at /v1/audio/transcriptions. Show the result and cost.
Use cases
Meeting archives
Process saved meeting recordings, prepared within the upload limit, into searchable text with timestamps.
Lecture transcripts
Transcribe lecture recordings prepared within the upload limit, then index or summarise the text for students.
Content moderation prep
Native sensitive-word masking is an Alibaba option, not listed in the model details here; filter the returned text on your side.
Prompt examples
Transcribe this 10-minute all-hands recording within the 25 MB limit and return the text.
Transcribe this lecture clip's audio and return the timed text.
Transcribe these weekly stand-up recordings, one file per request, and return the text.
FAQ
What is Paraformer v2 best for?
Offline transcription of recorded meetings, interviews, and conversations. Alibaba documents mainstream audio and video formats at any sample rate. Prepare uploads within the limit of the endpoint and follow the returned task status for completion.
How big can the input be?
Paraformer v2 is aimed at long meetings and conversations: Alibaba's native file service documents 12 hours or 2 GB per recording. The upload endpoint linked here is stricter, at 25 MB per file, and the native allowance does not raise it. Prepare every file within that size and track each job through its returned task status.
Can I turn timestamps off?
No. Alibaba states that timestamps are always enabled for Paraformer. Inspect the fields in the transcript response you actually receive before building on a specific timing structure.
Paraformer v2 or Fun-ASR?
Alibaba lists diarization and hotwords for both as native features; neither is in the model details linked here. Fun-ASR is the newer line; Paraformer v2 is the established one. Run a sample of your audio through each and compare the errors that matter to you.
How much does Paraformer v2 cost?
On TokenLab, Paraformer v2 costs $0.00001176 per second. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.
Which endpoint should Paraformer v2 use?
Use https://api.tokenlab.sh/v1/audio/transcriptions for Paraformer v2. The request example below shows the matching code shape.
Which operations does Paraformer v2 support?
Paraformer v2 supports Speech to text. Select an operation above to see its endpoint and request example.
Compare Paraformer v2
Sources
- Model Studio: recording file recognition models
- Model Studio: speech-to-text models for real-time and file transcription
Reviewed Oct 2, 2026